imsciences 0.9.6.5__py3-none-any.whl → 0.9.6.7__py3-none-any.whl

imsciences/pull.py

@@ -379,7 +379,7 @@ class datapull:
         
     ###############################################################  Seasonality  ##########################################################################
 
-    def pull_seasonality(self, week_commencing, start_date, countries):
+    def pull_seasonality(week_commencing, start_date, countries):
             """
             Generates a DataFrame with weekly seasonality features.
 
@@ -597,7 +597,7 @@ class datapull:
 
 
             # ---------------------------------------------------------------------
-            # 4. Add daily indicators for last day & last Friday of month
+            # 4. Add daily indicators for last day & last Friday of month & payday
             # ---------------------------------------------------------------------
             df_daily["is_last_day_of_month"] = df_daily["Date"].dt.is_month_end
 
@@ -608,22 +608,27 @@ class datapull:
                 # Check if next Friday is in the next month
                 next_friday = date + timedelta(days=7)
                 return 1 if next_friday.month != date.month else 0
+            
+            def is_payday(date):
+                return 1 if date.day >= 25 else 0
 
             df_daily["is_last_friday_of_month"] = df_daily["Date"].apply(is_last_friday)
-
+            
+            df_daily["is_payday"] = df_daily["Date"].apply(is_payday)
+            
             # Rename for clarity prefix
             df_daily.rename(columns={
                 "is_last_day_of_month": "seas_last_day_of_month",
-                "is_last_friday_of_month": "seas_last_friday_of_month"
+                "is_last_friday_of_month": "seas_last_friday_of_month",
+                "is_payday": "seas_payday"
             }, inplace=True)
 
-
             # ---------------------------------------------------------------------
             # 5. Weekly aggregation
             # ---------------------------------------------------------------------
 
             # Select only columns that are indicators/flags (intended for max aggregation)
-            flag_cols = [col for col in df_daily.columns if col.startswith('seas_') or col.startswith('is_')]
+            flag_cols = [col for col in df_daily.columns if (col.startswith('seas_') or col.startswith('is_')) and col != "seas_payday"]
             # Ensure 'week_start' is present for grouping
             df_to_agg = df_daily[['week_start'] + flag_cols]
 
@@ -635,7 +640,26 @@ class datapull:
                 .rename(columns={'week_start': "Date"})
                 .set_index("Date")
             )
+            
+            # Do specific aggregation for payday
+            # Make sure 'date' column exists in df_daily
+            df_daily["month"] = df_daily["Date"].dt.month
+            df_daily["year"] = df_daily["Date"].dt.year
+            
+            # Sum of seas_payday flags per week
+            week_payday_sum = df_daily.groupby("week_start")["seas_payday"].sum()
 
+            # Divide the number of payday flags by number of paydays per month
+            payday_days_in_month = (
+                df_daily.groupby(["year", "month"])["seas_payday"].sum()
+            )
+            week_month = df_daily.groupby("week_start").first()[["month", "year"]]
+            week_days_in_month = week_month.apply(lambda row: payday_days_in_month.loc[(row["year"], row["month"])], axis=1)
+            df_weekly_flags["seas_payday"] = (week_payday_sum / week_days_in_month).fillna(0).values
+
+            # # Drop intermediate columns
+            # df_weekly_flags = df_weekly_flags.drop(columns=["month", "year"])
+            
             # --- Aggregate Week Number using MODE ---
             # Define aggregation function for mode (handling potential multi-modal cases by taking the first)
             def get_mode(x):
@@ -678,7 +702,6 @@ class datapull:
             df_weekly_monthly_dummies.rename(columns={'week_start': 'Date'}, inplace=True)
             df_weekly_monthly_dummies.set_index('Date', inplace=True)
 
-
             # ---------------------------------------------------------------------
             # 6. Combine all weekly components
             # ---------------------------------------------------------------------
@@ -697,15 +720,15 @@ class datapull:
 
             # Ensure correct types for flag columns (int)
             for col in df_weekly_flags.columns:
-                if col in df_combined.columns:
-                    df_combined[col] = df_combined[col].astype(int)
+                if col != 'seas_payday':
+                    if col in df_combined.columns:
+                        df_combined[col] = df_combined[col].astype(int)
 
             # Ensure correct types for month columns (float)
             for col in df_weekly_monthly_dummies.columns:
                 if col in df_combined.columns:
                     df_combined[col] = df_combined[col].astype(float)
 
-
             # ---------------------------------------------------------------------
             # 7. Create weekly dummies for Week of Year & yearly dummies from aggregated cols
             # ---------------------------------------------------------------------
@@ -737,7 +760,7 @@ class datapull:
             # Filter out columns not in the desired order list (handles case where dum_ cols are off)
             final_cols = [col for col in cols_order if col in df_combined.columns]
             df_combined = df_combined[final_cols]
-
+            
             return df_combined
     
     def pull_weather(self, week_commencing, start_date, country_codes) -> pd.DataFrame:

{imsciences-0.9.6.5.dist-info → imsciences-0.9.6.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.6.5
+Version: 0.9.6.7
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.6.5.dist-info → imsciences-0.9.6.7.dist-info}/RECORD

@@ -1,12 +1,12 @@
 imsciences/__init__.py,sha256=_HuYeLbDMTdt7GpKI4r6-d7yRPZgcAQ7yOW0-ydR2Yo,117
 imsciences/geo.py,sha256=eenng7_BP_E2WD5Wt1G_oNxQS8W3t6lycRwJ91ngysY,15808
 imsciences/mmm.py,sha256=qMh0ccOepehfCcux7EeG8cq6piSEoFEz5iiJbDBWOS4,82214
-imsciences/pull.py,sha256=4NGKzNmsvfzADMucR8iLGTkYDyb5wdnqphe1CzepyWw,94992
+imsciences/pull.py,sha256=vABqnOFpNaFEnpc24tz1VyHrekOFFGoCsGpkevy3dyY,96362
 imsciences/unittesting.py,sha256=U177_Txg0Lqn49zYRu5bl9OVe_X7MkNJ6V_Zd6DHOsU,45656
 imsciences/vis.py,sha256=2izdHQhmWEReerRqIxhY4Ai10VjL7xoUqyWyZC7-2XI,8931
-imsciences-0.9.6.5.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
-imsciences-0.9.6.5.dist-info/METADATA,sha256=37dZ6LLY_2Vh9j06P1MUa9TNriZANXzE3CNEOpvC-BM,18846
-imsciences-0.9.6.5.dist-info/PKG-INFO-TomG-HP-290722,sha256=RMcthCSyWmU6IBsXGL-nYqw0RP06pzjPKK3dzOQcU-8,18846
-imsciences-0.9.6.5.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
-imsciences-0.9.6.5.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.9.6.5.dist-info/RECORD,,
+imsciences-0.9.6.7.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
+imsciences-0.9.6.7.dist-info/METADATA,sha256=hcZHA2Nc1wwtaaXM92ozcCHXHlfMdIikSCgbzdL5z0U,18846
+imsciences-0.9.6.7.dist-info/PKG-INFO-TomG-HP-290722,sha256=RMcthCSyWmU6IBsXGL-nYqw0RP06pzjPKK3dzOQcU-8,18846
+imsciences-0.9.6.7.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+imsciences-0.9.6.7.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.9.6.7.dist-info/RECORD,,

{imsciences-0.9.6.5.dist-info → imsciences-0.9.6.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (74.1.0)
+Generator: setuptools (75.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any